Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.8927. Min Act: -0.1700
Data Index: 6635448 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.8927. Min Act: -0.1700
Data Index: 2877011 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.8927. Min Act: -0.1700
Data Index: 670987 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.8302. Min Act: -0.1700
Data Index: 1411580 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.8302. Min Act: -0.1700
Data Index: 3951537 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.7677. Min Act: -0.1700
Data Index: 7858631 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.7677. Min Act: -0.1700
Data Index: 4562944 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.7052. Min Act: -0.1700
Data Index: 581026 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.7052. Min Act: -0.1700
Data Index: 1625287 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.6427. Min Act: -0.1700
Data Index: 4569296 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.6427. Min Act: -0.1700
Data Index: 581025 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.6427. Min Act: -0.1700
Data Index: 519760 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.5802. Min Act: -0.1700
Data Index: 2079084 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.5802. Min Act: -0.1700
Data Index: 1111327 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.5802. Min Act: -0.1700
Data Index: 2814501 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.5802. Min Act: -0.1700
Data Index: 7988732 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.5177. Min Act: -0.1700
Data Index: 1613201 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.5177. Min Act: -0.1700
Data Index: 6168681 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.5177. Min Act: -0.1700
Data Index: 7865489 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8927. Min Range: -7.8927
Max Act: 7.5177. Min Act: -0.1700
Data Index: 1118384 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19